Move Context back to the third column

Right after SCI, where it was. The audit takes the budget cells from the
end of the row rather than at a fixed offset, so a reference column added
in front cannot shift which cells it reads.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

Author: barretodavid

bench/audit.py

@@ -407,10 +407,10 @@ def chart_labels(svg):
         bad_cell.append(f"{label}: not a leaderboard row")
         continue
     files = (_mm.get(spec.partition("@")[0], {}).get("gguf") or {}).get("files") or {}
-    # SCI leads and Context trails, so the budget columns are the cells between,
-    # in VRAM_BUDGETS order. Sliced from both ends rather than counted from one,
-    # so adding a trailing column cannot silently shift which cells are read.
-    tds = re.findall(r'<td class="r[^"]*"[^>]*>(.*?)</td>', rest, re.S)[1:-1]
+    # SCI and Context lead, so the budget columns are the last len(VRAM_BUDGETS)
+    # cells, in that order. Taken from the END rather than by a fixed offset, so
+    # another reference column added in front cannot shift which cells are read.
+    tds = re.findall(r'<td class="r[^"]*"[^>]*>(.*?)</td>', rest, re.S)[-len(VRAM_BUDGETS):]
     if len(tds) != len(VRAM_BUDGETS):
         bad_cell.append(f"{label}: {len(tds)} budget cells, expected {len(VRAM_BUDGETS)}")
         continue

bench/html_report.py

@@ -1172,12 +1172,8 @@ def h2h_stats(spec):
             # the index rides along so this table can be read in score order too,
             # which is the order it ships in; the models table above has the rest
             + num_td(r["sci"], f'{r["sci"]:.1f}')
-            # Context sits after the budget columns rather than before them: it is
-            # reference, not the answer, and in front it pushed every budget column
-            # off a 390px screen.
-            + cells
             + num_td(mm["context_length"], fmt_ctx(mm["context_length"]))
-            + "</tr>"
+            + cells + "</tr>"
         )
 
     # every sortable table on the page, not one by id: the open-weight table
@@ -1235,7 +1231,7 @@ def h2h_stats(spec):
   <p class="takeaway" style="margin:0 0 10px">The weights do not get the whole machine, so each column reserves room for the OS, the KV cache and activations: {budget_reserve_note}. A quant in <b>full black</b> is <b>Q6 or better</b>, where quantization is not the thing holding the model back; a greyed one is a 4-to-5-bit compromise.</p>
   <p class="takeaway" style="margin:0 0 10px">A blank means <b>nothing 4-bit or better fits</b>, which is a real answer rather than a missing one: below 4-bit degradation stops being minor and coding feels it first, so no cell recommends going lower. {too_big_note}</p>
   <div class="tablewrap"><table id="opentable" class="sortable">
-    <tr><th>Model</th><th class="r desc" data-num aria-sort="descending">SCI</th>{"".join(f'<th class="r" data-num>{b} GB</th>' for b in VRAM_BUDGETS)}<th class="r" data-num>Context</th></tr>
+    <tr><th>Model</th><th class="r desc" data-num aria-sort="descending">SCI</th><th class="r" data-num>Context</th>{"".join(f'<th class="r" data-num>{b} GB</th>' for b in VRAM_BUDGETS)}</tr>
     {"".join(open_rows_html)}
   </table></div>
 </section>"""

results/report.html

@@ -372,8 +372,8 @@ <h2 id="which-quantization-for-my-machine"><a class="anchor" href="#which-quanti
   <p class="takeaway" style="margin:0 0 10px">The weights do not get the whole machine, so each column reserves room for the OS, the KV cache and activations: 16 GB at 128, 8 GB at 64, 4 GB at 32, 4 GB at 24. A quant in <b>full black</b> is <b>Q6 or better</b>, where quantization is not the thing holding the model back; a greyed one is a 4-to-5-bit compromise.</p>
   <p class="takeaway" style="margin:0 0 10px">A blank means <b>nothing 4-bit or better fits</b>, which is a real answer rather than a missing one: below 4-bit degradation stops being minor and coding feels it first, so no cell recommends going lower. The nine open models not listed need more than 128 GB even at 4-bit: Kimi K3, MiMo-V2.5-Pro, MiniMax M3, DeepSeek V4 Flash, Qwen3.8 Max, DeepSeek V4-Pro, Hy3, Inkling and GLM 5.2.</p>
   <div class="tablewrap"><table id="opentable" class="sortable">
-    <tr><th>Model</th><th class="r desc" data-num aria-sort="descending">SCI</th><th class="r" data-num>128 GB</th><th class="r" data-num>64 GB</th><th class="r" data-num>32 GB</th><th class="r" data-num>24 GB</th><th class="r" data-num>Context</th></tr>
-    <tr><td>Muse Glimmer 30B</td><td class="r" data-s="53.54335822195509">53.5</td><td class="r fits" data-s="29.6"><span class="q">Q8_0</span> <span class="gb">30 GB</span></td><td class="r fits" data-s="29.6"><span class="q">Q8_0</span> <span class="gb">30 GB</span></td><td class="r fits" data-s="24.1"><span class="q">Q6_K_L</span> <span class="gb">24 GB</span></td><td class="r nofit" data-s="19.4"><span class="q">Q5_K_S</span> <span class="gb">19 GB</span></td><td class="r" data-s="131072">131k</td></tr><tr><td>gpt-oss-120b</td><td class="r" data-s="17.741231416968965">17.7</td><td class="r nofit" data-s="62.8"><span class="q">Q4_K_M</span> <span class="gb">63 GB</span></td><td class="r"></td><td class="r"></td><td class="r"></td><td class="r" data-s="131072">131k</td></tr><tr><td>Qwen3.6-35B-A3B</td><td class="r" data-s="16.19082483091965">16.2</td><td class="r fits" data-s="36.9"><span class="q">Q8_0</span> <span class="gb">37 GB</span></td><td class="r fits" data-s="36.9"><span class="q">Q8_0</span> <span class="gb">37 GB</span></td><td class="r fits" data-s="26.6"><span class="q">UD-Q5_K_XL</span> <span class="gb">27 GB</span></td><td class="r nofit" data-s="19.5"><span class="q">UD-IQ4_NL_XL</span> <span class="gb">20 GB</span></td><td class="r" data-s="262144">262k</td></tr><tr><td>Gemma 4 31B</td><td class="r" data-s="15.806948103252044">15.8</td><td class="r fits" data-s="32.6"><span class="q">Q8_0</span> <span class="gb">33 GB</span></td><td class="r fits" data-s="32.6"><span class="q">Q8_0</span> <span class="gb">33 GB</span></td><td class="r fits" data-s="27.5"><span class="q">UD-Q6_K_XL</span> <span class="gb">28 GB</span></td><td class="r nofit" data-s="18.3"><span class="q">Q4_K_M</span> <span class="gb">18 GB</span></td><td class="r" data-s="262144">262k</td></tr><tr><td>Qwen3 Coder Next</td><td class="r" data-s="14.283251268776736">14.3</td><td class="r fits" data-s="84.8"><span class="q">Q8_0</span> <span class="gb">85 GB</span></td><td class="r nofit" data-s="55.8"><span class="q">UD-Q5_K_S</span> <span class="gb">56 GB</span></td><td class="r"></td><td class="r"></td><td class="r" data-s="262144">262k</td></tr><tr><td>Qwen3.6-27B</td><td class="r" data-s="13.317904173386546">13.3</td><td class="r fits" data-s="28.6"><span class="q">Q8_0</span> <span class="gb">29 GB</span></td><td class="r fits" data-s="28.6"><span class="q">Q8_0</span> <span class="gb">29 GB</span></td><td class="r fits" data-s="25.6"><span class="q">UD-Q6_K_XL</span> <span class="gb">26 GB</span></td><td class="r fits" data-s="20.0"><span class="q">UD-Q5_K_XL</span> <span class="gb">20 GB</span></td><td class="r" data-s="262144">262k</td></tr>
+    <tr><th>Model</th><th class="r desc" data-num aria-sort="descending">SCI</th><th class="r" data-num>Context</th><th class="r" data-num>128 GB</th><th class="r" data-num>64 GB</th><th class="r" data-num>32 GB</th><th class="r" data-num>24 GB</th></tr>
+    <tr><td>Muse Glimmer 30B</td><td class="r" data-s="53.54335822195509">53.5</td><td class="r" data-s="131072">131k</td><td class="r fits" data-s="29.6"><span class="q">Q8_0</span> <span class="gb">30 GB</span></td><td class="r fits" data-s="29.6"><span class="q">Q8_0</span> <span class="gb">30 GB</span></td><td class="r fits" data-s="24.1"><span class="q">Q6_K_L</span> <span class="gb">24 GB</span></td><td class="r nofit" data-s="19.4"><span class="q">Q5_K_S</span> <span class="gb">19 GB</span></td></tr><tr><td>gpt-oss-120b</td><td class="r" data-s="17.741231416968965">17.7</td><td class="r" data-s="131072">131k</td><td class="r nofit" data-s="62.8"><span class="q">Q4_K_M</span> <span class="gb">63 GB</span></td><td class="r"></td><td class="r"></td><td class="r"></td></tr><tr><td>Qwen3.6-35B-A3B</td><td class="r" data-s="16.19082483091965">16.2</td><td class="r" data-s="262144">262k</td><td class="r fits" data-s="36.9"><span class="q">Q8_0</span> <span class="gb">37 GB</span></td><td class="r fits" data-s="36.9"><span class="q">Q8_0</span> <span class="gb">37 GB</span></td><td class="r fits" data-s="26.6"><span class="q">UD-Q5_K_XL</span> <span class="gb">27 GB</span></td><td class="r nofit" data-s="19.5"><span class="q">UD-IQ4_NL_XL</span> <span class="gb">20 GB</span></td></tr><tr><td>Gemma 4 31B</td><td class="r" data-s="15.806948103252044">15.8</td><td class="r" data-s="262144">262k</td><td class="r fits" data-s="32.6"><span class="q">Q8_0</span> <span class="gb">33 GB</span></td><td class="r fits" data-s="32.6"><span class="q">Q8_0</span> <span class="gb">33 GB</span></td><td class="r fits" data-s="27.5"><span class="q">UD-Q6_K_XL</span> <span class="gb">28 GB</span></td><td class="r nofit" data-s="18.3"><span class="q">Q4_K_M</span> <span class="gb">18 GB</span></td></tr><tr><td>Qwen3 Coder Next</td><td class="r" data-s="14.283251268776736">14.3</td><td class="r" data-s="262144">262k</td><td class="r fits" data-s="84.8"><span class="q">Q8_0</span> <span class="gb">85 GB</span></td><td class="r nofit" data-s="55.8"><span class="q">UD-Q5_K_S</span> <span class="gb">56 GB</span></td><td class="r"></td><td class="r"></td></tr><tr><td>Qwen3.6-27B</td><td class="r" data-s="13.317904173386546">13.3</td><td class="r" data-s="262144">262k</td><td class="r fits" data-s="28.6"><span class="q">Q8_0</span> <span class="gb">29 GB</span></td><td class="r fits" data-s="28.6"><span class="q">Q8_0</span> <span class="gb">29 GB</span></td><td class="r fits" data-s="25.6"><span class="q">UD-Q6_K_XL</span> <span class="gb">26 GB</span></td><td class="r fits" data-s="20.0"><span class="q">UD-Q5_K_XL</span> <span class="gb">20 GB</span></td></tr>
   </table></div>
 </section>